检索结果-内蒙古大学图书馆

A Population Initialization Method Based on Similarity and Mutual information in Evolutionary Algorithm for Bi-Objective Feature Selection

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第3期4卷 1-21页

作者： Cai, Xu Xue, Yu Artificial Intelligence Research Institute School of Information and Control Engineering China University of Mining and Technology Xuzhou China School of Software Nanjing University of Information Science and Technology Nanjing China

Feature selection (FS) is an important data pre-processing technique in classification. It aims to remove redundant and irrelevant features from the data, which reduces the dimensionality of data and improves the performance of the classifier. Thus, FS is a bi-objective optimization problem, and evolutionary algorithms (EAs) have been proven to be effective in solving bi-objective FS problems. EA is a population-based metaheuristic algorithm, and the quality of the initial population is an important factor affecting the performance of EA. An improper initial population may negatively affect the convergence speed of the EA and even make the algorithm fall into the local optimum. In this article, we propose a similarity and mutual information-based initialization method, named SMII, to improve the quality of the initial population. This method determines the distribution of initial solutions based on similarity and shields features with high correlation to the selected features according to mutual information. In the experiment, we embed SMII, the latest four initialization methods, and a traditional random initialization method into NSGA-II and compared their performance on 15 public datasets. The experimental results show that SMII performs best on most datasets and can effectively improve the performance of the algorithm. Moreover, we compare the performance of two other EAs before and after embedding SMII on 15 datasets, and the results further prove that the proposed method can effectively improve the search capability of the EA for FS. © 2024 Copyright held by the owner/author(s).

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Compliant control of Lower Limb Rehabilitation Exoskeleton Robot Based on Flexible Transmission

引用

Journal of Bionic engineering 2023年第3期20卷 1021-1035页

作者： Keping Liu Li Li Wanting Li Jian Gu Zhongbo Sun Department of Control Science and Engineering Changchun University of TechnologyChangchun130012China Department of Electrical and Information Engineering Jilin Engineering Normal UniversityChangchun130052China

To ensure the safety, comfort, and effectiveness of lower limb rehabilitation exoskeleton robots in the rehabilitation training process, compliance is a prerequisite for human–machine interaction safety. First, under the premise of considering the mechanical structure of the lower limb rehabilitation exoskeleton robot (LLRER), when conducting the dynamic transmission of the exoskeleton knee joint, the soft axis is added to ensure that the rotation motion and torque are flexibly transmitted to any position to achieve flexible force transmission. Second, to realize the active compliance control of LLRER, the sliding mode impedance closed-loop controller is developed based on the kinematics and dynamics model of LLRER, and the stability of the designed control system is verified by Lyapunov method. Then the experiment is designed to track the collected bicycle rehabilitation motion data stably, and the algorithm and dynamic model are verified to satisfy the experimental requirements. Finally, aiming at the transmission efficiency and response performance of the soft shaft in the torque transmission process of the knee joint, the soft shaft transmission performance test is carried out to test the soft shaft transmission performance and realize the compliance of the LLRER, so as to ensure that the rehabilitation training can be carried out in a safe and comfortable interactive environment. Through the design of rehabilitation exercise training, it is verified that the LLRER of flexible transmission under sliding mode impedance control has good adaptability in the actual environment, and can achieve accurate and flexible control. During the experiment, the effectiveness of monitoring rehabilitation training is brought through the respiratory belt.

关键词： Lower limb rehabilitation exoskeleton Flexible control Impedance control Stability

来源：评论

学校读者我要写书评

暂无评论

Dynamic Charging and Path Planning for UAV-Powered Rechargeable WSNs Using Multi-Agent Deep Reinforcement Learning

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 15610-15626页

作者： Betalo, Mesfin Leranso Leng, Supeng Seid, Abegaz Mohammed Abishu, Hayla Nahom Erbad, Aiman Bai, Xiaoshan Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar Shenzhen University College of Mechatronics and Control Engineering National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

Unmanned Aerial Vehicle (UAV)-powered 5G/6G networks integrated with rechargeable wireless sensor networks (RWSNs) offer promising solutions for extending system lifetime, collecting data, and providing computing services and power to sensor nodes (SNs). UAVs offer significant advantages, including exceptional mobility, cost-effective deployment, and the ability to be easily reprogrammed for a wide range of missions. However, the limited onboard power capacity of UAVs, coupled with the lack of dynamic and intelligent charging station (CS) management and inefficient path planning, can lead to SN failure in dynamic mobile environments. To address these challenges, we propose an energy-efficient laser-charged UAV (LCU)-enabled RWSN environment, wherein UAVs, powered by laser beams from ground-based stations, provide services, collect data, and transfer energy to SNs. We formulate a joint optimization problem involving power allocation, dynamic charging strategy (DCS), and path planning to minimize task completion time and sensor node death time. Given the NP-hard nature of the problem, we employ a stochastic game model based on a Markov decision process (MDP) for its solution. To solve this problem, we propose a deep reinforcement learning (DRL) based algorithm that enables real-time charging scheduling decisions while optimizing network performance. We introduce a multi-agent double deep Q-network (MA-DDQN) model to determine the optimal trajectories for all UAVs in large and complex environments. Simulation results demonstrate that the MA-DDQN approach outperforms state-of-the-art techniques, showing significant improvements in terms of average delay, energy consumption, and task completion time. © 2004-2012 IEEE.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

UViT: Efficient and lightweight U-shaped hybrid vision transformer for human pose estimation

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8345-8359页

作者： Li, Biao Tang, Shoufeng Li, Wenyi School of Information and Control Engineering China University of Mining and Technology Xuzhou China School of Mechanical and Electronic Engineering Suzhou University Suzhou China

Pose estimation plays a crucial role in human-centered vision applications and has advanced significantly in recent years. However, prevailing approaches use extremely complex structural designs for obtaining high scores on the benchmark dataset, hampering edge device applications. In this study, an efficient and lightweight human pose estimation problem is investigated. Enhancements are made to the context enhancement module of the U-shaped structure to improve the multi-scale local modeling capability. With a transformer structure, a lightweight transformer block was designed to enhance the local feature extraction and global modeling ability. Finally, a lightweight pose estimation network-U-shaped Hybrid Vision Transformer, UViT-was developed. The minimal network UViT-T achieved a 3.9% improvement in AP scores on the COCO validation set with fewer model parameters and computational complexity compared with the best-performing V2 version of the MobileNet series. Specifically, with an input size of 384×288, UViT-T achieves an impressive AP score of 70.2 on the COCO test-dev set, with only 1.52 M parameters and 2.32 GFLOPs. The inference speed is approximately twice that of general-purpose networks. This study provides an efficient and lightweight design idea and method for the human pose estimation task and provides theoretical support for its deployment on edge devices. © 2024-IOS Press. All rights reserved.

关键词： Structural design

来源：评论

学校读者我要写书评

暂无评论

Range Ambiguous Clutter Suppression and Moving Target Indication for Side-looking Airborne Radar with Vertical Coherent FDA 16

Range Ambiguous Clutter Suppression and Moving Target Indica...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Lu, Jiahao Zhang, Mengdi Li, Shiyin School of Information and Control Engineering China University of Mining and Technology China

ISBN: (纸本)9781510689251

Under the high pulse repetition frequency (PRF) regime, a serious range ambiguity problem arises in the moving target indication (MTI) radar, leading to a degradation in the performance of traditional space-time adaptive processing (STAP). To address this issue, a range ambiguous clutter suppression and MTI method based on vertical coherent frequency diverse array (FDA) is proposed in this paper. The space-frequency coupling characteristic of vertical coherent FDA is revealed, and a series of two-dimensional (2-D) matched filters are designed to separate range ambiguous clutter and resolve the range ambiguity of targets. After matched filtering, clutter in the desired range region may be contaminated by sidelobes or even mainlobes of clutter from other range regions. To eliminate residual clutter, the azimuth phase coding (APC) technique is applied to induce different Doppler frequency shifts for different range regions. Subsequently, the residual clutter can be eliminated through orthogonal subspace projection (OSP) technique. However, APC also induces a Doppler shift to the target, affecting the accurate acquisition of target information. To this end, Doppler compensation is applied to the echo after the elimination of residual clutter. Finally, traditional STAP is performed on the echoes corresponding to different range regions. Additionally, due to the use of coherent waveforms, it prevents unreal orthogonal waveform assumption in multi-input multi-output (MIMO) framework. Simulation results are provided to validate the effectiveness of the proposed method, demonstrating its capability to enhance the performance of MTI radar under high PRF conditions. © 2025 SPIE.

关键词： Space time adaptive processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced UAV Pursuit-Evasion Using Boids Modelling:A Synergistic Integration of Bird Swarm Intelligence and DRL

引用

Computers, Materials & Continua 2024年第9期80卷 3523-3553页

作者： Weiqiang Jin Xingwu Tian Bohang Shi Biao Zhao Haibin Duan Hao Wu School of Information and Communications Engineering Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an710049China China Academy of Electronics and Information Technology China Electronics Technology Group Corporation(CETC)Beijing100041China Department ofAutomatic Control School of Automation Science and Electrical EngineeringBeihangUniversityBeijing100191China

TheUAV pursuit-evasion problem focuses on the efficient tracking and capture of evading targets using unmanned aerial vehicles(UAVs),which is pivotal in public safety applications,particularly in scenarios involving intrusion monitoring and *** address the challenges of data acquisition,real-world deployment,and the limited intelligence of existing algorithms in UAV pursuit-evasion tasks,we propose an innovative swarm intelligencebased UAV pursuit-evasion control framework,namely“Boids Model-based DRL Approach for Pursuit and Escape”(Boids-PE),which synergizes the strengths of swarm intelligence from bio-inspired algorithms and deep reinforcement learning(DRL).The Boids model,which simulates collective behavior through three fundamental rules,separation,alignment,and cohesion,is adopted in our *** integrating Boids model with the Apollonian Circles algorithm,significant improvements are achieved in capturing UAVs against simple evasion *** further enhance decision-making precision,we incorporate a DRL algorithm to facilitate more accurate strategic *** also leverage self-play training to continuously optimize the performance of pursuit *** experimental evaluation,we meticulously designed both one-on-one and multi-to-one pursuit-evasion scenarios,customizing the state space,action space,and reward function models for each *** simulations,supported by the PyBullet physics engine,validate the effectiveness of our proposed *** overall results demonstrate that Boids-PE significantly enhance the efficiency and reliability of UAV pursuit-evasion tasks,providing a practical and robust solution for the real-world application of UAV pursuit-evasion missions.

关键词： UAV pursuit-evasion swarm intelligence algorithm Boids model deep reinforcement learning self-play training

来源：评论

学校读者我要写书评

暂无评论

Research and application of composite stochastic resonance in enhancement detection

引用

Chinese Physics B 2024年第1期33卷 264-273页

作者：高蕊焦尚彬薛琼婕 School of Automation and Information Engineering Xi'an University of TechnologyXi'an 710048China School of Electronic and Electrical Engineering Baoji University of Arts and SciencesBaoji 721016China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of TechnologyXi'an 710048China

Aiming at the problem that the intermediate potential part of the traditional bistable stochastic resonance model cannot be adjusted independently, a new composite stochastic resonance(NCSR) model is proposed by combining the Woods–Saxon(WS) model and the improved piecewise bistable model. The model retains the characteristics of the independent parameters of WS model and the improved piecewise model has no output saturation, all the parameters in the new model have no coupling characteristics. Under α stable noise environment, the new model is used to detect periodic signal and aperiodic signal, the detection results indicate that the new model has higher noise utilization and better detection ***, the new model is applied to image denoising, the results showed that under the same conditions, the output peak signal-to-noise ratio(PSNR) and the correlation number of NCSR method is higher than that of other commonly used linear denoising methods and improved piecewise SR methods, the effectiveness of the new model is verified.

关键词： Woods–Saxon improved piecewise model composite stochastic resonance(SR) image denoising

来源：评论

学校读者我要写书评

暂无评论

Research on non-uniform heat transfer testing of prefabricated walls based on infrared images

引用

建筑模拟（英文版） 2025年第3期18卷 499-513页

作者： Dalong Liu Guoqian Wang Bencheng Feng Lihong Jiang Songshu Hu College of Architecture Xi'an University of Architecture and TechnologyXi'an 710055China College of Information and Control Engineering Xi'an University of Architecture and TechnologyXi'an 710399China Shanghai Jianke Engineering Consulting Co. Ltd.Shanghai 200032China

The combination of prefabricated type and low energy consumption has become the core development trend of the construction ***,existing studies often overlook non-uniform heat transfer testing of prefabricated walls based on infrared *** paper aims to proposes a comprehensive evaluation index,incorporating cumulative temperature difference ratio and equivalent heat transfer coefficient,to analyze the non-uniform heat transfer characteristics of prefabricated exterior *** impact of non-uniform heat transfer on prefabricated exterior walls is assessed through non-uniform influence area and exterior wall heat transfer *** enhance efficiency,we employ image segmentation technology utilizing infrared thermal imaging to analyze and detect the non-uniform heat transfer patterns of prefabricated *** EM algorithm of an improved Gaussian mixture model is utilized for multi-classification on thermal imaging images,identifying non-uniform heat transfer affected areas and calculating the effective heat transfer *** results demonstrate the efficacy of a three-class Gaussian mixture model for visualizing non-uniform heat transfer influence *** image segmentation algorithm,improved based on the K-means clustering algorithm,exhibits superior performance in terms of PSNR,SSIM,and FSIM ***,the proposed method enables automatic calculation of cumulative temperature difference ratio and equivalent heat transfer coefficient,showing within 5%and 10%error,respectively,compared to measured *** study establishes a preliminary automatic recognition and calculation mode for thermal performance parameters of prefabricated *** findings can provide a convenient and rapid analysis of prefabricated walls thermal performance.

关键词： prefabricated building infrared thermal imaging Gaussian mixture model wall heat transfer non-uniformity

来源：评论

学校读者我要写书评

暂无评论

Predictor and ESO-based adaptive tracking control of heterogeneous vehicle platoon

引用

Science China(Technological Sciences) 2024年第9期67卷 2842-2852页

作者： SUN ZhiZe LIU Yang ZHANG LinChuang College of Control Science and Engineering Bohai UniversityJinzhou 121013China College of Automation and Electronic Engineering Qingdao University of Science and TechnologyQingdao 266061China College of Information Science and Technology Bohai UniversityJinzhou 121013China

This paper investigates the distributed adaptive platoon tracking problem of third-order heterogeneous vehicles subject to model uncertainties. The design process is divided into two steps. Firstly, an adaptive tracking controller is designed for the dynamic leading vehicle. And then, the distributed adaptive controllers are established for followers. Moreover, the predictor technique is used to improve the estimate performance of the adaptive law, and the total disturbance is approximated and compensated by the variable gain nonlinear extended state observers(NESOs) driven by the estimation error. By introducing the variable gain hyperbolic tangent tracking differentiator(HTTD), the “complexity explosion” problem is avoided. The feasibility and effectiveness of the proposed protocol are verified by simulation tests.

关键词： variable gain NESOs heterogeneous vehicles platoon tracking predictor

来源：评论

学校读者我要写书评

暂无评论

DCL-depth: monocular depth estimation network based on iam and depth consistency loss

引用

Multimedia Tools and Applications 2025年第8期84卷 4773-4787页

作者： Han, Chenggong Lv, Chen Kou, Qiqi Jiang, He Cheng, Deqiang The School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The School of Computer Science and Technology China University of Mining and Technology Xuzhou221116 China

The self-supervised monocular depth estimation algorithm obtains excellent results in outdoor environments. However, traditional self-supervised depth estimation methods often suffer from edge blurring in complex textured regions and the loss of depth information in pixels within weakly-textured areas. To enhance the perception ability of the deep network for complex textured areas and the accuracy of depth estimation in weakly-textured regions, the following methods are proposed in this paper. First of all, the image activity measure (IAM) is used to segment the image features. Based on the multi-directional distribution of image contours, the network's perception ability has been improved, resulting in effective enhancement of depth estimation in complex regions. Furthermore, a new loss function called depth consistency loss (DCL) is proposed, which is based on recursive recurrent networks. The DCL aims to measure the similarity between the output images of the first-order network and the second-order network, and the network's constraint on weak-texture regions has been strengthened. By employing this approach, the accuracy of estimating depth information in weakly-textured regions can be enhanced. Through adequate experimentation on the public indoor datasets, the results show that our network outperforms the compared algorithms in terms of accuracy and visualization of predicted depth. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：